© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 64317
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    symbols and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Calvert
    -0.50
    psis
    -0.47
     Volk
    -0.46
    pyplot
    -0.45
    IntoConstraints
    -0.45
    UIAlert
    -0.44
    ostasis
    -0.44
    ultz
    -0.43
    ocal
    -0.42
    bbers
    -0.42
    POSITIVE LOGITS
    }{|
    0.47
     $|
    0.47
    uxxxx
    0.45
    |}
    0.45
     |
    0.44
    .|
    0.42
     $|\
    0.42
    DataAnnotations
    0.41
    |
    0.41
     avoient
    0.40
    Activations Density 0.004%

    No Known Activations